编译与链接

#include <stdio.h>
int main()
{
  printf("Hello World\n");
  return 0;
}

在Linux下，当我们使用GCC来编译Hello World程序时，只需使用最简单的命令： 

mali@mali:~/code/link$ cat hello.c 
#include <stdio.h>
int main()
{
  printf("Hello World\n");
  return 0;
}
mali@mali:~/code/link$ gcc hello.c
mali@mali:~/code/link$ ls -l
total 16
-rwxrwxr-x 1 mali mali 8600 9月   3 23:20 a.out
-rw-rw-r-- 1 mali mali   73 9月   3 23:19 hello.c
mali@mali:~/code/link$ ./a.out
Hello World
mali@mali:~/code/link$ 

事实上，上述过程可以分解为4个步骤，分别是预处理(Preprocessing)、编译(Compilation)、汇编(Assembly)和链接(Linking)。

1.预处理(Preprocessing)

mali@mali:~/code/link$ gcc -E hello.c -o hello.i
mali@mali:~/code/link$ ls -l
total 36
-rwxrwxr-x 1 mali mali  8600 9月   3 23:20 a.out
-rw-rw-r-- 1 mali mali    73 9月   3 23:19 hello.c
-rw-rw-r-- 1 mali mali 17103 9月   3 23:25 hello.i
mali@mali:~/code/link$ cat hello.i
# 1 "hello.c"
# 1 "<built-in>"
# 1 "<command-line>"
# 1 "/usr/include/stdc-predef.h" 1 3 4
# 1 "<command-line>" 2
# 1 "hello.c"
# 1 "/usr/include/stdio.h" 1 3 4
# 27 "/usr/include/stdio.h" 3 4
# 1 "/usr/include/features.h" 1 3 4
# 367 "/usr/include/features.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 1 3 4
# 410 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/wordsize.h" 1 3 4
# 411 "/usr/include/x86_64-linux-gnu/sys/cdefs.h" 2 3 4
# 368 "/usr/include/features.h" 2 3 4
# 391 "/usr/include/features.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/gnu/stubs.h" 1 3 4
# 10 "/usr/include/x86_64-linux-gnu/gnu/stubs.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/gnu/stubs-64.h" 1 3 4
# 11 "/usr/include/x86_64-linux-gnu/gnu/stubs.h" 2 3 4
# 392 "/usr/include/features.h" 2 3 4
# 28 "/usr/include/stdio.h" 2 3 4





# 1 "/usr/lib/gcc/x86_64-linux-gnu/5/include/stddef.h" 1 3 4
# 216 "/usr/lib/gcc/x86_64-linux-gnu/5/include/stddef.h" 3 4

# 216 "/usr/lib/gcc/x86_64-linux-gnu/5/include/stddef.h" 3 4
typedef long unsigned int size_t;
# 34 "/usr/include/stdio.h" 2 3 4

# 1 "/usr/include/x86_64-linux-gnu/bits/types.h" 1 3 4
# 27 "/usr/include/x86_64-linux-gnu/bits/types.h" 3 4
# 1 "/usr/include/x86_64-linux-gnu/bits/wordsize.h" 1 3 4
# 28 "/usr/include/x86_64-linux-gnu/bits/types.h" 2 3 4


typedef unsigned char __u_char;
typedef unsigned short int __u_short;
typedef unsigned int __u_int;
typedef unsigned long int __u_long;


typedef signed char __int8_t;
typedef unsigned char __uint8_t;
typedef signed short int __int16_t;
typedef unsigned short int __uint16_t;
typedef signed int __int32_t;
typedef unsigned int __uint32_t;

typedef signed long int __int64_t;
typedef unsigned long int __uint64_t;
...
extern int fileno (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;




extern int fileno_unlocked (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;
# 872 "/usr/include/stdio.h" 3 4
extern FILE *popen (const char *__command, const char *__modes) ;





extern int pclose (FILE *__stream);





extern char *ctermid (char *__s) __attribute__ ((__nothrow__ , __leaf__));
# 912 "/usr/include/stdio.h" 3 4
extern void flockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));



extern int ftrylockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__)) ;


extern void funlockfile (FILE *__stream) __attribute__ ((__nothrow__ , __leaf__));
# 942 "/usr/include/stdio.h" 3 4

# 2 "hello.c" 2

# 2 "hello.c"
int main()
{
  printf("Hello World\n");
  return 0;
}
mali@mali:~/code/link$ 

2.编译(Compilation)

mali@mali:~/code/link$ gcc -S hello.i -o hello.s
mali@mali:~/code/link$ ls -l
total 40
-rwxrwxr-x 1 mali mali  8600 9月   3 23:20 a.out
-rw-rw-r-- 1 mali mali    73 9月   3 23:19 hello.c
-rw-rw-r-- 1 mali mali 17103 9月   3 23:25 hello.i
-rw-rw-r-- 1 mali mali   456 9月   3 23:33 hello.s
mali@mali:~/code/link$ cat hello.s
	.file	"hello.c"
	.section	.rodata
.LC0:
	.string	"Hello World"
	.text
	.globl	main
	.type	main, @function
main:
.LFB0:
	.cfi_startproc
	pushq	%rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	movq	%rsp, %rbp
	.cfi_def_cfa_register 6
	movl	$.LC0, %edi
	call	puts
	movl	$0, %eax
	popq	%rbp
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE0:
	.size	main, .-main
	.ident	"GCC: (Ubuntu 5.4.0-6ubuntu1~16.04.10) 5.4.0 20160609"
	.section	.note.GNU-stack,"",@progbits
mali@mali:~/code/link$ 

3.汇编(Assembly)

mali@mali:~/code/link$ gcc -c hello.s -o hello.o
mali@mali:~/code/link$ ls -l
total 44
-rwxrwxr-x 1 mali mali  8600 9月   3 23:20 a.out
-rw-rw-r-- 1 mali mali    73 9月   3 23:19 hello.c
-rw-rw-r-- 1 mali mali 17103 9月   3 23:25 hello.i
-rw-rw-r-- 1 mali mali  1504 9月   3 23:35 hello.o
-rw-rw-r-- 1 mali mali   456 9月   3 23:33 hello.s
mali@mali:~/code/link$ objdump -d hello.o

hello.o:     file format elf64-x86-64


Disassembly of section .text:

0000000000000000 <main>:
   0:	55                   	push   %rbp
   1:	48 89 e5             	mov    %rsp,%rbp
   4:	bf 00 00 00 00       	mov    $0x0,%edi
   9:	e8 00 00 00 00       	callq  e <main+0xe>
   e:	b8 00 00 00 00       	mov    $0x0,%eax
  13:	5d                   	pop    %rbp
  14:	c3                   	retq   
mali@mali:~/code/link$ 

4.链接(Linking)

0000000000400400 <puts@plt>:
  400400:	ff 25 12 0c 20 00    	jmpq   *0x200c12(%rip)        # 601018 <_GLOBAL_OFFSET_TABLE_+0x18>
  400406:	68 00 00 00 00       	pushq  $0x0
  40040b:	e9 e0 ff ff ff       	jmpq   4003f0 <_init+0x28>

0000000000400526 <main>:
  400526:	55                   	push   %rbp
  400527:	48 89 e5             	mov    %rsp,%rbp
  40052a:	bf c4 05 40 00       	mov    $0x4005c4,%edi
  40052f:	e8 cc fe ff ff       	callq  400400 <puts@plt>
  400534:	b8 00 00 00 00       	mov    $0x0,%eax
  400539:	5d                   	pop    %rbp
  40053a:	c3                   	retq   
  40053b:	0f 1f 44 00 00       	nopl   0x0(%rax,%rax,1)

mali@mali:~/code/link$ gcc hello.o -o hello
mali@mali:~/code/link$ ls -l
total 56
-rwxrwxr-x 1 mali mali  8600 9月   3 23:20 a.out
-rwxrwxr-x 1 mali mali  8600 9月   3 23:50 hello
-rw-rw-r-- 1 mali mali    73 9月   3 23:19 hello.c
-rw-rw-r-- 1 mali mali 17103 9月   3 23:25 hello.i
-rw-rw-r-- 1 mali mali  1504 9月   3 23:35 hello.o
-rw-rw-r-- 1 mali mali   456 9月   3 23:33 hello.s
mali@mali:~/code/link$ objdump -d hello

hello:     file format elf64-x86-64


Disassembly of section .init:

00000000004003c8 <_init>:
  4003c8:	48 83 ec 08          	sub    $0x8,%rsp
  4003cc:	48 8b 05 25 0c 20 00 	mov    0x200c25(%rip),%rax        # 600ff8 <_DYNAMIC+0x1d0>
  4003d3:	48 85 c0             	test   %rax,%rax
  4003d6:	74 05                	je     4003dd <_init+0x15>
  4003d8:	e8 43 00 00 00       	callq  400420 <__libc_start_main@plt+0x10>
  4003dd:	48 83 c4 08          	add    $0x8,%rsp
  4003e1:	c3                   	retq   

Disassembly of section .plt:

00000000004003f0 <puts@plt-0x10>:
  4003f0:	ff 35 12 0c 20 00    	pushq  0x200c12(%rip)        # 601008 <_GLOBAL_OFFSET_TABLE_+0x8>
  4003f6:	ff 25 14 0c 20 00    	jmpq   *0x200c14(%rip)        # 601010 <_GLOBAL_OFFSET_TABLE_+0x10>
  4003fc:	0f 1f 40 00          	nopl   0x0(%rax)

0000000000400400 <puts@plt>:
  400400:	ff 25 12 0c 20 00    	jmpq   *0x200c12(%rip)        # 601018 <_GLOBAL_OFFSET_TABLE_+0x18>
  400406:	68 00 00 00 00       	pushq  $0x0
  40040b:	e9 e0 ff ff ff       	jmpq   4003f0 <_init+0x28>

0000000000400410 <__libc_start_main@plt>:
  400410:	ff 25 0a 0c 20 00    	jmpq   *0x200c0a(%rip)        # 601020 <_GLOBAL_OFFSET_TABLE_+0x20>
  400416:	68 01 00 00 00       	pushq  $0x1
  40041b:	e9 d0 ff ff ff       	jmpq   4003f0 <_init+0x28>

Disassembly of section .plt.got:

0000000000400420 <.plt.got>:
  400420:	ff 25 d2 0b 20 00    	jmpq   *0x200bd2(%rip)        # 600ff8 <_DYNAMIC+0x1d0>
  400426:	66 90                	xchg   %ax,%ax

Disassembly of section .text:

0000000000400430 <_start>:
  400430:	31 ed                	xor    %ebp,%ebp
  400432:	49 89 d1             	mov    %rdx,%r9
  400435:	5e                   	pop    %rsi
  400436:	48 89 e2             	mov    %rsp,%rdx
  400439:	48 83 e4 f0          	and    $0xfffffffffffffff0,%rsp
  40043d:	50                   	push   %rax
  40043e:	54                   	push   %rsp
  40043f:	49 c7 c0 b0 05 40 00 	mov    $0x4005b0,%r8
  400446:	48 c7 c1 40 05 40 00 	mov    $0x400540,%rcx
  40044d:	48 c7 c7 26 05 40 00 	mov    $0x400526,%rdi
  400454:	e8 b7 ff ff ff       	callq  400410 <__libc_start_main@plt>
  400459:	f4                   	hlt    
  40045a:	66 0f 1f 44 00 00    	nopw   0x0(%rax,%rax,1)

0000000000400460 <deregister_tm_clones>:
  400460:	b8 3f 10 60 00       	mov    $0x60103f,%eax
  400465:	55                   	push   %rbp
  400466:	48 2d 38 10 60 00    	sub    $0x601038,%rax
  40046c:	48 83 f8 0e          	cmp    $0xe,%rax
  400470:	48 89 e5             	mov    %rsp,%rbp
  400473:	76 1b                	jbe    400490 <deregister_tm_clones+0x30>
  400475:	b8 00 00 00 00       	mov    $0x0,%eax
  40047a:	48 85 c0             	test   %rax,%rax
  40047d:	74 11                	je     400490 <deregister_tm_clones+0x30>
  40047f:	5d                   	pop    %rbp
  400480:	bf 38 10 60 00       	mov    $0x601038,%edi
  400485:	ff e0                	jmpq   *%rax
  400487:	66 0f 1f 84 00 00 00 	nopw   0x0(%rax,%rax,1)
  40048e:	00 00 
  400490:	5d                   	pop    %rbp
  400491:	c3                   	retq   
  400492:	0f 1f 40 00          	nopl   0x0(%rax)
  400496:	66 2e 0f 1f 84 00 00 	nopw   %cs:0x0(%rax,%rax,1)
  40049d:	00 00 00 

00000000004004a0 <register_tm_clones>:
  4004a0:	be 38 10 60 00       	mov    $0x601038,%esi
  4004a5:	55                   	push   %rbp
  4004a6:	48 81 ee 38 10 60 00 	sub    $0x601038,%rsi
  4004ad:	48 c1 fe 03          	sar    $0x3,%rsi
  4004b1:	48 89 e5             	mov    %rsp,%rbp
  4004b4:	48 89 f0             	mov    %rsi,%rax
  4004b7:	48 c1 e8 3f          	shr    $0x3f,%rax
  4004bb:	48 01 c6             	add    %rax,%rsi
  4004be:	48 d1 fe             	sar    %rsi
  4004c1:	74 15                	je     4004d8 <register_tm_clones+0x38>
  4004c3:	b8 00 00 00 00       	mov    $0x0,%eax
  4004c8:	48 85 c0             	test   %rax,%rax
  4004cb:	74 0b                	je     4004d8 <register_tm_clones+0x38>
  4004cd:	5d                   	pop    %rbp
  4004ce:	bf 38 10 60 00       	mov    $0x601038,%edi
  4004d3:	ff e0                	jmpq   *%rax
  4004d5:	0f 1f 00             	nopl   (%rax)
  4004d8:	5d                   	pop    %rbp
  4004d9:	c3                   	retq   
  4004da:	66 0f 1f 44 00 00    	nopw   0x0(%rax,%rax,1)

00000000004004e0 <__do_global_dtors_aux>:
  4004e0:	80 3d 51 0b 20 00 00 	cmpb   $0x0,0x200b51(%rip)        # 601038 <__TMC_END__>
  4004e7:	75 11                	jne    4004fa <__do_global_dtors_aux+0x1a>
  4004e9:	55                   	push   %rbp
  4004ea:	48 89 e5             	mov    %rsp,%rbp
  4004ed:	e8 6e ff ff ff       	callq  400460 <deregister_tm_clones>
  4004f2:	5d                   	pop    %rbp
  4004f3:	c6 05 3e 0b 20 00 01 	movb   $0x1,0x200b3e(%rip)        # 601038 <__TMC_END__>
  4004fa:	f3 c3                	repz retq 
  4004fc:	0f 1f 40 00          	nopl   0x0(%rax)

0000000000400500 <frame_dummy>:
  400500:	bf 20 0e 60 00       	mov    $0x600e20,%edi
  400505:	48 83 3f 00          	cmpq   $0x0,(%rdi)
  400509:	75 05                	jne    400510 <frame_dummy+0x10>
  40050b:	eb 93                	jmp    4004a0 <register_tm_clones>
  40050d:	0f 1f 00             	nopl   (%rax)
  400510:	b8 00 00 00 00       	mov    $0x0,%eax
  400515:	48 85 c0             	test   %rax,%rax
  400518:	74 f1                	je     40050b <frame_dummy+0xb>
  40051a:	55                   	push   %rbp
  40051b:	48 89 e5             	mov    %rsp,%rbp
  40051e:	ff d0                	callq  *%rax
  400520:	5d                   	pop    %rbp
  400521:	e9 7a ff ff ff       	jmpq   4004a0 <register_tm_clones>

0000000000400526 <main>:
  400526:	55                   	push   %rbp
  400527:	48 89 e5             	mov    %rsp,%rbp
  40052a:	bf c4 05 40 00       	mov    $0x4005c4,%edi
  40052f:	e8 cc fe ff ff       	callq  400400 <puts@plt>
  400534:	b8 00 00 00 00       	mov    $0x0,%eax
  400539:	5d                   	pop    %rbp
  40053a:	c3                   	retq   
  40053b:	0f 1f 44 00 00       	nopl   0x0(%rax,%rax,1)

0000000000400540 <__libc_csu_init>:
  400540:	41 57                	push   %r15
  400542:	41 56                	push   %r14
  400544:	41 89 ff             	mov    %edi,%r15d
  400547:	41 55                	push   %r13
  400549:	41 54                	push   %r12
  40054b:	4c 8d 25 be 08 20 00 	lea    0x2008be(%rip),%r12        # 600e10 <__frame_dummy_init_array_entry>
  400552:	55                   	push   %rbp
  400553:	48 8d 2d be 08 20 00 	lea    0x2008be(%rip),%rbp        # 600e18 <__init_array_end>
  40055a:	53                   	push   %rbx
  40055b:	49 89 f6             	mov    %rsi,%r14
  40055e:	49 89 d5             	mov    %rdx,%r13
  400561:	4c 29 e5             	sub    %r12,%rbp
  400564:	48 83 ec 08          	sub    $0x8,%rsp
  400568:	48 c1 fd 03          	sar    $0x3,%rbp
  40056c:	e8 57 fe ff ff       	callq  4003c8 <_init>
  400571:	48 85 ed             	test   %rbp,%rbp
  400574:	74 20                	je     400596 <__libc_csu_init+0x56>
  400576:	31 db                	xor    %ebx,%ebx
  400578:	0f 1f 84 00 00 00 00 	nopl   0x0(%rax,%rax,1)
  40057f:	00 
  400580:	4c 89 ea             	mov    %r13,%rdx
  400583:	4c 89 f6             	mov    %r14,%rsi
  400586:	44 89 ff             	mov    %r15d,%edi
  400589:	41 ff 14 dc          	callq  *(%r12,%rbx,8)
  40058d:	48 83 c3 01          	add    $0x1,%rbx
  400591:	48 39 eb             	cmp    %rbp,%rbx
  400594:	75 ea                	jne    400580 <__libc_csu_init+0x40>
  400596:	48 83 c4 08          	add    $0x8,%rsp
  40059a:	5b                   	pop    %rbx
  40059b:	5d                   	pop    %rbp
  40059c:	41 5c                	pop    %r12
  40059e:	41 5d                	pop    %r13
  4005a0:	41 5e                	pop    %r14
  4005a2:	41 5f                	pop    %r15
  4005a4:	c3                   	retq   
  4005a5:	90                   	nop
  4005a6:	66 2e 0f 1f 84 00 00 	nopw   %cs:0x0(%rax,%rax,1)
  4005ad:	00 00 00 

00000000004005b0 <__libc_csu_fini>:
  4005b0:	f3 c3                	repz retq 

Disassembly of section .fini:

00000000004005b4 <_fini>:
  4005b4:	48 83 ec 08          	sub    $0x8,%rsp
  4005b8:	48 83 c4 08          	add    $0x8,%rsp
  4005bc:	c3                   	retq   
mali@mali:~/code/link$